ferosai / feros
Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.
Why this job: says: voice agent; topics: text-to-speech, speech-recognition, speech-to-text, voice-ai
What it does
We built Feros to solve the structural problems of the current voice AI ecosystem. With a Rust runtime engineered for sub-second latency, an AI-driven builder, and a Python control plane—all in a single self-hostable monorepo—we address these barriers head-on:
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 5 months ago
- Stars
- 115
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.2.0
- Released 6 months ago
- Built with
- Rust
- 47% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 64% closed
- 5 still open
- Pull requests
- 73 merged
- 0 waiting
- Releases
- 2
- 2 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| QwenAudio / qwen-audio-agent | 3,178 | 4 days ago | Apache-2.0 | Mac, Windows |
| gradio-app / fastrtc | 4,636 | 19 days ago | MIT | No downloads |
| deepgram / deepgram-python-sdk | 479 | 5 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Rust 47%
- Python 24%
- TypeScript 20%
- C 8%
Topics
- agent-framework
- agentic-ai
- automation-platform
- conversational-ai
- enterprise-ai
- multi-language
- open-source
- real-time
- self-hosted
- speech-recognition
- speech-to-text
- text-to-speech
Project record
- JobSpeech and audio
- StatusListed
- Commits98
- Forks20
- Watching3
- Stars in 28 days+2
- CreatedApr 6, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026